x86: Check all 0s/1s vectors with standard_sse_constant_p

commit 77473a27bae04da99d6979d43e7bd0a8106f4557
Author: H.J. Lu <hjl.tools@gmail.com>
Date:   Thu Jun 26 06:08:51 2025 +0800

    x86: Also handle all 1s float vector constant

replaces

(insn 29 28 30 5 (set (reg:V2SF 107)
        (mem/u/c:V2SF (symbol_ref/u:DI ("*.LC0") [flags 0x2]) [0  S8 A64])) 2031 {*movv2sf_internal}
     (expr_list:REG_EQUAL (const_vector:V2SF [
                (const_double:SF -QNaN [-QNaN]) repeated x2
            ])
        (nil)))

with

(insn 98 13 14 3 (set (reg:V8QI 112)
        (const_vector:V8QI [
                (const_int -1 [0xffffffffffffffff]) repeated x8
            ])) -1
     (nil))
...
(insn 29 28 30 5 (set (reg:V2SF 107)
        (subreg:V2SF (reg:V8QI 112) 0)) 2031 {*movv2sf_internal}
     (expr_list:REG_EQUAL (const_vector:V2SF [
                (const_double:SF -QNaN [-QNaN]) repeated x2
            ])
        (nil)))

which leads to

pr121015.c: In function ‘render_result_from_bake_h’:
pr121015.c:34:1: error: unrecognizable insn:
   34 | }
      | ^
(insn 98 13 14 3 (set (reg:V8QI 112)
        (const_vector:V8QI [
                (const_int -1 [0xffffffffffffffff]) repeated x8
            ])) -1
     (expr_list:REG_EQUIV (const_vector:V8QI [
                (const_int -1 [0xffffffffffffffff]) repeated x8
            ])
        (nil)))
during RTL pass: ira

Check all 0s/1s vectors with standard_sse_constant_p to avoid unsupported
all 1s vectors.

Co-Developed-by: H.J. Lu <hjl.tools@gmail.com>
gcc/

	PR target/121015
	* config/i386/i386-features.cc (ix86_broadcast_inner): Check all
	0s/1s vectors with standard_sse_constant_p.

gcc/testsuite/

	PR target/121015
	* gcc.target/i386/pr121015.c: New test.

diff --git a/gcc/config/i386/i386-features.cc b/gcc/config/i386/i386-features.cc
index 054f8d5ddc8276e6f878f94c788f6f037568f552..734ab70c108479c288bdb0761f8b0b63554b6cdb 100644 (file)
--- a/gcc/config/i386/i386-features.cc
+++ b/gcc/config/i386/i386-features.cc
@@ -3534,22 +3534,20 @@ ix86_broadcast_inner (rtx op, machine_mode mode,
                      machine_mode *scalar_mode_p,
                      x86_cse_kind *kind_p, rtx_insn **insn_p)
 {
-  if (op == const0_rtx || op == CONST0_RTX (mode))
+  switch (standard_sse_constant_p (op, mode))
     {
+    case 1:
       *scalar_mode_p = QImode;
       *kind_p = X86_CSE_CONST0_VECTOR;
       *insn_p = nullptr;
       return const0_rtx;
-    }
-  else if ((GET_MODE_CLASS (mode) == MODE_VECTOR_INT
-           && (op == constm1_rtx || op == CONSTM1_RTX (mode)))
-           || (GET_MODE_CLASS (mode) == MODE_VECTOR_FLOAT
-               && float_vector_all_ones_operand (op, mode)))
-    {
+    case 2:
       *scalar_mode_p = QImode;
       *kind_p = X86_CSE_CONSTM1_VECTOR;
       *insn_p = nullptr;
       return constm1_rtx;
+    default:
+      break;
     }
 
   mode = GET_MODE (op);

diff --git a/gcc/testsuite/gcc.target/i386/pr121015.c b/gcc/testsuite/gcc.target/i386/pr121015.c
new file mode 100644 (file)
index 0000000..57c8bff
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr121015.c
@@ -0,0 +1,32 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -march=x86-64-v3" } */
+
+extern union {
+  int i;
+  float f;
+} int_as_float_u;
+
+extern int render_result_from_bake_w;
+extern int render_result_from_bake_h_seed_pass;
+extern float *render_result_from_bake_h_primitive;
+extern float *render_result_from_bake_h_seed;
+
+float
+int_as_float(int i)
+{
+  int_as_float_u.i = i;
+  return int_as_float_u.f;
+}
+
+void
+render_result_from_bake_h(int tx)
+{
+  while (render_result_from_bake_w) {
+    for (; tx < render_result_from_bake_w; tx++)
+      render_result_from_bake_h_primitive[1] =
+          render_result_from_bake_h_primitive[2] = int_as_float(-1);
+    if (render_result_from_bake_h_seed_pass) {
+      *render_result_from_bake_h_seed = 0;
+    }
+  }
+}